Patentable/Patents/US-7853079
US-7853079

Technique for automatic poster frame detection

PublishedDecember 14, 2010
Assigneenot available in USPTO data we have
Inventorsnot available in USPTO data we have
Technical Abstract

A technique that may be used to configure a computer system to automatically search a video and select a frame within the video clip that best represents the content of that video. A frame contained in a video is identified. Luminance values for each pixel in a plurality of pixels contained in the frame are then generated. The frame is then selected as a poster frame for the video if a luminance value for at least one pixel in the plurality of pixels contained in the identified frame is outside a range of luminance values. The range of luminance values may be determined from a luminance value associated with a reference pixel contained in the frame.

Patent Claims
22 claims

Legal claims defining the scope of protection, as filed with the USPTO.

1

1. A method in a computerized device, the method comprising: identifying a frame in a plurality of frames contained in a video; generating a luminance value for each pixel in a plurality of pixels contained in the identified frame; and selecting the identified frame as a poster frame for the video if a luminance value for at least one pixel in the plurality of pixels contained in the identified frame is outside a predetermined range of luminance values, wherein the step of generating a luminance value for each pixel further comprises: dividing the identified frame into a plurality of blocks; and for each block in the plurality of blocks: (a) generating a luminance value for a reference pixel contained in the block, and (b) generating a luminance value for one or more additional pixels contained in the block; wherein the step of selecting the identified frame further comprises: determining the range of luminance values from the generated luminance value for the reference pixel; for each block in the plurality of blocks: (a) comparing the generated luminance values for the one or more additional pixels with the range of luminance values, and (b) concluding the block is good if one or more luminance values for the one or more additional pixels are outside the range of the luminance values; and selecting the identified frame as the poster frame for the video based on a number of blocks concluded to be good.

2

2. A method as defined in claim 1 wherein the range of luminance values is determined from a luminance value associated with a reference pixel contained in the frame.

3

3. A method as defined in claim 1 wherein the step of identifying a frame among a plurality of frames in a video further comprises: dividing the video into a plurality of time intervals, each time interval containing one or more frames of the video; identifying a time interval in the plurality of time intervals; and identifying the frame from the one or more frames contained in the identified time interval.

4

4. A method as defined in claim 1 further comprising: generating a luminance value for a reference pixel in the plurality of pixels; and determining the range of luminance values from the generated luminance value for the reference pixel.

5

5. A method as defined in claim 1 wherein the step of selecting further comprises: comparing the generated luminance values with the range of luminance values; and selecting the identified frame as the poster frame for the video if the result of the comparison indicates that one or more luminance values are outside the range of luminance values.

6

6. The method as in claim 1 , comprising: wherein generating a luminance value for each pixel in a plurality of pixels contained in the identified frame includes: identifying at least one reference pixel from the plurality of pixels; and for each pixel in the plurality of pixels, identifying a color intensity occurring in each pixel, the color intensity represented via the luminance value of the respective pixel, wherein the color intensity relates to at least one color in the respective pixel; and wherein selecting the identified frame as a poster frame for the video includes: selecting the identified frame as the poster frame upon detecting a number of pixels in the plurality of pixels each have a respective color intensity occurring outside a range, wherein a color intensity occurring in the reference pixel falls between an upper boundary of the range and a lower boundary of the range, wherein the poster frame comprises multi-colored content, occurring in the video, selected to visually represent the overall content of the video.

7

7. The method as in claim 6 , wherein selecting the identified frame as the poster frame for the video includes: creating the poster frame as a selectable thumbnail which, upon selection, initiates playback of the video.

8

8. The method as in claim 1 , comprising: wherein generating a luminance value for each pixel in a plurality of pixels contained in the identified frame includes: identifying at least one reference pixel from the plurality of pixels; and for each pixel in the plurality of pixels, identifying an extent of a brightness of at least one color occurring in each respective pixel, the extent of the brightness of the at least one color represented via the luminance value of the respective pixel; and wherein selecting the identified frame as a poster frame for the video includes: selecting the identified frame as the poster frame upon detecting a number of pixels in the plurality of pixels each have a respective extent of brightness of the at least one color occurring outside a range, wherein an extent of brightness of at least one color occurring in the reference pixel falls between an upper boundary of the range and a lower boundary of the range, wherein the poster frame comprises multi-colored content, occurring in the video, selected to visually represent the overall content of the video.

9

9. An apparatus comprising: a data storage configured to hold a plurality of frames contained in a video; and a processor configured to: (a) identify a frame in a plurality of frames contained in a video, (b) generate a luminance value for each pixel in a plurality of pixels contained in the identified frame, and (c) select the identified frame as a poster frame for the video if a luminance value for at least one pixel in the plurality of pixels contained in the identified frame is outside a predetermined range of luminance values, wherein the processor is further configured to: (a) divide the frame into a plurality of blocks, and (b) for each block in the plurality of blocks: (1) generate a luminance value for a reference pixel contained in the block, and (2) generate a luminance value for one or more additional pixels contained in the block, wherein the processor is further configured to: (a) determine the range of luminance values from the generated luminance value for the reference pixel, (b) for each block in the plurality of blocks: (1) compare the generated luminance values for the one or more additional pixels with the range of luminance values, (2) conclude the block is good if a predetermined number of luminance values for the one or more additional pixels are outside the range of the luminance values, and (c) select the identified frame as the poster frame for the video based on a number of blocks concluded to be good.

10

10. An apparatus as defined in claim 9 wherein the range of luminance values is determined from a luminance value associated with a reference pixel contained in the frame.

11

11. An apparatus as defined in claim 9 wherein the processor is further configured to: (a) divide the video into a plurality of time intervals, each time interval containing one or more frames of the video, (b) identify a time interval in the plurality of time intervals, and (c) identify the frame from the one or more frames contained in the identified time interval.

12

12. An apparatus as defined in claim 9 wherein the processor is further configured to: (a) generate a luminance value for a reference pixel in the plurality of pixels, and (b) determine the range of luminance values from the generated luminance value for the reference pixel.

13

13. An apparatus as defined in claim 9 wherein the processor is further configured to: (a) compare the generated luminance values with the range of luminance values, and (b) select the identified frame as the poster frame for the video if the result of the comparison indicates that one or more luminance values are outside the range of luminance values.

14

14. A non-transitory computer-readable medium comprising computer-executable instructions for: identifying a frame in a plurality of frames contained in a video; generating a luminance value for each pixel in a plurality of pixels contained in the identified frame; and selecting the identified frame as a poster frame for the video if a luminance value for at least one pixel in the plurality of pixels contained in the identified frame is outside a predetermined range of luminance values; wherein generating the luminance value for each pixel includes: dividing the identified frame into a plurality of blocks; for each block in the plurality of blocks: (a) generating a luminance value for a reference pixel contained in the block, and (b) generating a luminance value for one or more additional pixels contained in the block; wherein selecting the identified frame further comprises: determining the range of luminance values from the generated luminance value for the reference pixel; for each block in the plurality of blocks: (a) comparing the generated luminance values for the one or more additional pixels with the range of luminance values, and (b) concluding the block is good if one or more luminance values for the one or more additional pixels are outside the range of the luminance values; and selecting the identified frame as the poster frame for the video based on a number of blocks concluded to be good.

15

15. A non-transitory computer-readable medium as defined in claim 14 wherein the range of luminance values is determined from a luminance value associated with a reference pixel contained in the frame.

16

16. A non-transitory computer-readable medium as defined in claim 14 further comprising computer-executable instructions for: dividing the video into a plurality of time intervals, each time interval containing one or more frames of the video; identifying a time interval in the plurality of time intervals; and identifying the frame from the one or more frames contained in the identified time interval.

17

17. A non-transitory computer-readable medium as defined in claim 14 further comprising computer-executable instructions for: generating a luminance value for a reference pixel in the plurality of reference pixels; and determining the range of luminance values from the generated luminance value for the reference pixel.

18

18. A non-transitory computer-readable medium as defined in claim 14 further comprising computer-executable instructions for: comparing the generated luminance values with the range of luminance values; and selecting the identified frame as the poster frame for the video if the result of the comparison indicates that one or more luminance values are outside the range of luminance values.

19

19. A method in a computerized device, the method comprising: (a) dividing a video into one or more time intervals, each time interval containing one or more frames; (b) selecting a time interval from the one or more time intervals; (c) identifying a frame in the time interval; (d) dividing the identified frame into a plurality of blocks, each block containing a plurality of pixels contained in the frame; (e) for one or more blocks in the plurality of blocks: (1) identifying a reference pixel from the plurality of pixels contained in the block, (2) generating a luminance value for the identified reference pixel, (3) determining a range of luminance values from the generated luminance value for the identified reference pixel, (4) generating luminance values for one or more additional pixels contained in the block, (5) determining if any of the luminance values for the additional pixels are outside of the range of luminance values, and (6) concluding the block is a good if any of the luminance values for the additional pixels are outside the range of luminance values; and (f) selecting the frame as a poster frame for the video based on a number of blocks concluded to be good.

20

20. A method in a computerized device, the method comprising: identifying a frame in a plurality of frames contained in a video; generating a luminance value for each pixel in a plurality of pixels contained in the identified frame; and selecting the identified frame as a poster frame for the video if a luminance value for at least one pixel in the plurality of pixels contained in the identified frame is outside a predetermined range of luminance values, wherein generating a luminance value for each pixel in a plurality of pixels contained in the identified frame includes: identifying a plurality of frame portions within the identified frame; and for each frame portion in the plurality of frame portions: (i) selecting at least one pixel, from a group of pixels, as a reference, the group of pixels located in the respective frame portion; (ii) identifying a color intensity occurring in each pixel in the group of pixels, the color intensity represented via the luminance value of the respective pixel, wherein the color intensity relates to at least one color in the respective pixel; (iii) identifying the respective frame portion as a bad frame portion unless at least one pixel in the group of pixels has a respective color intensity occurring outside a range, wherein a color intensity occurring in the reference falls between an upper boundary of the range and a lower boundary of the range; and (iv) if at least one pixel in the group of pixels has the respective color intensity occurring outside the range, identifying the respective frame portion as a good frame portion.

21

21. The method as in claim 20 , wherein selecting the identified frame as a poster frame for the video includes: selecting the identified frame as the poster frame upon detecting the identified frame has at least a pre-determined number of good frame portions, wherein the poster frame comprises multi-colored content, occurring in the video, selected to visually represent the overall content of the video.

22

22. A method in a computerized device, the method comprising: identifying a frame in a plurality of frames contained in a video; generating a luminance value for each pixel in a plurality of pixels contained in the identified frame; and selecting the identified frame as a poster frame for the video if a luminance value for at least one pixel in the plurality of pixels contained in the identified frame is outside a predetermined range of luminance values, wherein the range of luminance values is determined from a luminance value associated with a single reference pixel contained in the frame.

Classification Codes (CPC)

Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.

Patent Metadata

Filing Date

December 8, 2006

Publication Date

December 14, 2010

Want to explore more patents?

Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.

Citation & reuse

Analysis on this page is generated by Patentable — an AI-powered patent intelligence platform. AI-generated summaries, explanations, and analysis may be reused with attribution and a visible link back to the canonical URL below. Patent abstracts and claims are USPTO public domain.

Cite as: Patentable. “Technique for automatic poster frame detection” (US-7853079). https://patentable.app/patents/US-7853079

© 2026 Patentable. All rights reserved.

Patentable is a research and drafting-assistant tool, not a law firm, and does not provide legal advice. Documents we generate are drafts for review by a licensed patent attorney.